© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101793
    Prev
    Next
    INDEX
    Explanations

    cooked smoked

    np_acts-logits-general · gemini-2.5-flash-lite

    technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⵓ
    0.50
     prenn
    0.50
    desPort
    0.50
    philosoph
    0.49
    燧
    0.48
    渶
    0.47
    opposition
    0.47
    隶
    0.46
    izuje
    0.46
     allant
    0.44
    POSITIVE LOGITS
     も
    0.45
     メル
    0.45
     ဗ
    0.44
     大阪
    0.43
     Vegetables
    0.43
     general
    0.43
     constexpr
    0.42
    রান
    0.41
    数
    0.41
     respuesta
    0.40
    Activations Density 0.001%

    No Known Activations